Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Time-Series Representation Learning via Temporal and Contextual Contrasting

About

Learning decent representations from unlabeled time-series data with temporal dynamics is a very challenging task. In this paper, we propose an unsupervised Time-Series representation learning framework via Temporal and Contextual Contrasting (TS-TCC), to learn time-series representation from unlabeled data. First, the raw time-series data are transformed into two different yet correlated views by using weak and strong augmentations. Second, we propose a novel temporal contrasting module to learn robust temporal representations by designing a tough cross-view prediction task. Last, to further learn discriminative representations, we propose a contextual contrasting module built upon the contexts from the temporal contrasting module. It attempts to maximize the similarity among different contexts of the same sample while minimizing similarity among contexts of different samples. Experiments have been carried out on three real-world time-series datasets. The results manifest that training a linear classifier on top of the features learned by our proposed TS-TCC performs comparably with the supervised training. Additionally, our proposed TS-TCC shows high efficiency in few-labeled data and transfer learning scenarios. The code is publicly available at https://github.com/emadeldeen24/TS-TCC.

Emadeldeen Eldele, Mohamed Ragab, Zhenghua Chen, Min Wu, Chee Keong Kwoh, Xiaoli Li, Cuntai Guan• 2021

Related benchmarks

TaskDatasetResultRank
Multivariate ForecastingETTh1
MSE0.653
686
Time Series ForecastingETTh1 (test)
MSE0.653
348
Multivariate Time-series ForecastingWeather
MSE0.572
340
ECG ClassificationPTBXL Super
Macro AUC78.9
84
Time-series classificationSelfRegulationSCP2
Accuracy57.5
79
Time-series classificationHeartbeat
Accuracy69
75
Time-series classificationUWaveGestureLibrary
Accuracy92
71
Time-series classificationPEMS-SF
Accuracy73
69
Time-series classificationHandwriting
Accuracy55
62
Time Series ForecastingETT1
RMSE0.75
62
Showing 10 of 91 rows
...

Other info

Code

Follow for update